Leveraging Neural Network Phrase Embedding Model for Query Reformulation in Ad-Hoc Biomedical Information Retrieval

Abstract

This study presents a spark enhanced neural network phrase embedding model to leverage query representation for relevant biomedical literature retrieval. Information retrieval for clinical decision support demands high precision. In recent years, word embeddings have been evolved as a solution to such requirements. It represents vocabulary words in low-dimensional vectors in the context of their similar words; however, it is inadequate to deal with semantic phrases or multi-word units. Learning vector embeddings for phrases by maintaining word meanings is a challenging task. This study proposes a scalable phrase embedding technique to embed multi-word units into vector representations using a state-of-the-art word embedding technique, keeping both word and phrase in the same vectors space. It will enhance the effectiveness and efficiency of query language models by expanding unseen query terms and phrases for the semantically associated query terms. Embedding vectors are evaluated via a query expansion technique for ad-hoc retrieval task over two benchmark corpora viz. TREC-CDS 2014 collection with 733,138 PubMed articles and OHSUMED corpus having 348,566 articles collected from a Medline database. The results show that the proposed technique has significantly outperformed other state-of-the-art retrieval techniques

Query Reformulation for Indonesian Question Answering System Using Word Embedding of Word2Vec

“…Second, using a semantic dictionary (WordNet) and corpus statistics. New queries are generated by analyzing meaning relationships between words or word counts based on statistics [12]. This approach is more complicated than using Query Log because of its high semantic gap.…”